The Main Idea
Of BERT
Dhoni more Similar to Cummins than to Australia.
💎State of the art language model for NLP.
💎BERT makes use of Transformer, an attention mechanism that learns contextual relations between words (or sub-words) in a text.
💎Bert-large — has 24 encoders layers stacked on one of top of the other, 16 attention heads and consist of 1024 hidden units.
💎The total number of parameters Bert-large is 3400 million.
Dhoni more Similar to Cummins than to Australia.
Created with Mobirise
Free Offline Site Creator